A Hybrid LSTM and MLP Scheme for COVID-19 Prediction: A Case Study in Thailand
DOI:
https://doi.org/10.48048/tis.2023.6884Keywords:
COVID-19, Prediction, Long short-term memory (LSTM), Multilayer perceptron (MLP)Abstract
After the COVID-19 epidemic, Thailand was affected in a variety of ways, with the most obvious being the economic downturn and the huge impact on health, including the loss of medical and human resources to combat the epidemic. However, Thailand still lacks analysis and prediction tools required to prepare for future epidemic situations. Therefore, we present development models for predicting the spread of the COVID-19 epidemic. In particular, the application of a long short-term memory (LSTM) and multilayer perceptron (MLP) model was investigated to predict new cases, total cases, new deaths, and total deaths. There are a total of 77 provinces in Thailand. The data used in this trial were obtained from the Department of Disease Control (DDC) of the Thai government. The modeling employed 2 types of data: dynamic (time series) and static. There were 2 phases: 1) the LSTM was used to manipulate time series data and 2) the MLP model was used to manipulate static data. Then, the models were merged for further analysis. We evaluated the performance of the combined model, yielding an accuracy of 99.72 % based on R2 values, higher than the values obtained for state-of-the-art methods. In addition, the prediction results can be further combined with GIS data in each province and displayed via an easy-to-use web application for mapping.
HIGHLIGHTS
- A new architecture that can be used as a tool to predict the COVID-19 epidemic situation is proposed
- Deep learning is applied to create predictive models with LSTM for time series data and MLPs for static data
- A tool used for displaying predictions using a web application in the form of a map of each province in Thailand is developed to show the prediction results in detail
GRAPHICAL ABSTRACT
Downloads
Metrics
References
JH Zeng, YX Liu, J Yuan, FX Wang, WB Wu, JX Li, LF Wang, H Gao, Y Wang, CF Dong, YJ Li, XJ Xie, C Feng, L Liu. First case of COVID-19 complicated with fulminant myocarditis: A case report and insights. Infection 2020; 48, 773-7.
R Strugnell and W Nancy. Sustained neutralising antibodies in the Wuhan population suggest durable protection against SARS-CoV-2. Lancet 2021; 397, 1037-9.
YC Li, B Wan‐Zhu and H Tsutomu. The neuroinvasive potential of SARS‐CoV2 may play a role in the respiratory failure of COVID‐19 patients. J. Med. Virol. 2020; 92, 552-5.
Y Zoabi, S Deri-Rozov and Noam Shomron. Machine learning-based prediction of COVID-19 diagnosis based on symptoms. NPJ Digit. Med. 2021; 4, 3.
WHO Coronavirus (COVID-19) Dashboard, Available at: https://covid19.who.int/, accessed December 2022.
K Tantrakarnapa, B Bhopdhornangkul and K Nakhaapakorn. Influencing factors of COVID-19: A case study of Thailand. J. Publ. Health 2022; 30, 621-7.
B Leerapan, P Kaewkamjornchai, R Atun and MS Jalali. How systems respond to policies: Intended and unintended consequences of COVID-19 lockdown policies in Thailand. Health Pol. Plann. 2022; 37, 292-3.
K Pornpatanapaisansakul. FAQ Issue 171: Labor market digital transformation. Bank of Thailand, Bangkok, Thailand, 2020.
N Anusonphat and C Poompurk. New normal ways for the survival and adaptation of community enterprise after COVID-19 crisis of Thailand. J. MCU Nakhondhat 2022; 9, 1-19.
Ministry of Public Health. The report of COVID-19 situation in Thailand, Available at: https://ddc.moph.go.th/covid19-dashboard/, accessed December 2022.
S Montaha, S Azam, AKMRH Rafid, Z Hasan, A Karim. TimeDistributed-CNN-LSTM: A Hybrid approach combining CNN and LSTM to classify brain tumor on 3D MRI scans performing ablation study. IEEE Access 2022; 10, 60039-59.
Z Cheng, Z Yi and T Chengkai. Solving monocular sensors depth prediction using MLP-based architecture and multi-scale inverse attention. IEEE Sensor. J. 2022; 22, 16178-89.
O Tutsoy, Ş Çolak, A Polat and Kemal Balikci. A novel parametric model for the prediction and analysis of the COVID-19 casualties. IEEE Access 2020; 8, 193898-906.
Y Zhu, S Wang, S Wang, Q Wu, L Wang, H Li, M Wang, M Niu, Y Zha and J Tian. Mix contrast for COVID-19 mild-to-critical prediction. IEEE Trans. Biomed. Eng. 2021; 68, 3725-36.
S Tabik, A Gómez-Ríos, JL Martín-Rodríguez, I Sevillano-García, M Rey-Area, D Charte, E Guirado, JL Suárez, J Luengo, MA Valero-González, P García-Villanova, E Olmedo-Sánchez and F Herrera. COVIDGR dataset and COVID-SDNet methodology for predicting COVID-19 based on chest X-ray images. IEEE J. Biomed. Health Informat. 2020; 24, 3595-605.
C Moremada et al. Energy efficient contact tracing and social interaction-based patient prediction system for COVID-19 pandemic. J. Comm. Network. 2021; 23, 390-407.
D Vekaria, A Kumari, S Tanwar and N Kumar. ξboost: An AI-based data analytics scheme for COVID-19 prediction and economy boosting. IEEE Internet Things J. 2020; 8, 15977-89.
N Saeed, A Bader, TY Al-Naffouri and MS Alouini. When wireless communication responds to COVID-19: Combating the pandemic and saving the economy. Front. Comm. Network. 2020; 1, 566853.
OA Ehiorobo. Strategic agility and AI-enabled resource capabilities for business survival in post-COVID-19 global economy. Int. J. Informat. Bus. Manag. 2020; 12, 201-13.
D McCoy, W Mgbara, N Horvitz, WM Getz and Alan Hubbard. Ensemble machine learning of factors influencing COVID-19 across US counties. Sci. Rep. 2021; 11, 11777.
R Ma, X Zheng, P Wang, H Liu and C Zhang. The prediction and analysis of COVID-19 epidemic trend by combining LSTM and Markov method. Sci. Rep. 2021; 11, 17421.
BM Yahya, FS Yahya and RG Thannoun. COVID-19 prediction analysis using artificial intelligence procedures and GIS spatial analyst: A case study for Iraq. Appl. Geomat. 2021; 13, 481-91.
FM Khan, A Kumar, H Puppala, G Kumar and R Gupta. Projecting the criticality of COVID-19 transmission in India using GIS and machine learning methods. J. Saf. Sci. Resilience 2021; 2, 50-62.
B Niu, R Liang, S Zhang, H Zhang, X Qu, Q Su, L Zheng and Q Chen. Epidemic analysis of COVID‐19 in Italy based on spatiotemporal geographic information and Google trends. Transbound. Emerg. Dis. 2021; 68, 2384-400.
![](https://tis.wu.ac.th/public/journals/1/submission_6884_6884_coverImage_en_US.jpg)
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Walailak University
![Creative Commons License](http://i.creativecommons.org/l/by-nc-nd/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.